R${}^3$: Reinforced Reader-Ranker for Open-Domain Question Answering

Abstract

In recent years researchers have achieved considerable success applying neural network methods to question answering (QA). These approaches have achieved state of the art results in simplified closed-domain settings such as the SQuAD (Rajpurkar et al., 2016) dataset, which provides a pre-selected passage, from which the answer to a given question may be extracted. More recently, researchers have begun to tackle open-domain QA, in which the model is given a question and access to a large corpus (e.g., wikipedia) instead of a pre-selected passage (Chen et al., 2017a). This setting is more complex as it requires large-scale search for relevant passages by an information retrieval component, combined with a reading comprehension model that "reads" the passages to generate an answer to the question. Performance in this setting lags considerably behind closed-domain performance. In this paper, we present a novel open-domain QA system called Reinforced Ranker-Reader $(R^3)$, based on two algorithmic innovations. First, we propose a new pipeline for open-domain QA with a Ranker component, which learns to rank retrieved passages in terms of likelihood of generating the ground-truth answer to a given question. Second, we propose a novel method that jointly trains the Ranker along with an answer-generation Reader model, based on reinforcement learning. We report extensive experimental results showing that our method significantly improves on the state of the art for multiple open-domain QA datasets.

arXiv comment8 pages, accepted by AAAI 2018

References in corpus (11)

• Enhanced LSTM for Natural Language Inference
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Large-scale Simple Question Answering with Memory Networks
• Machine Comprehension Using Match-LSTM and Answer Pointer
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• Quasar: Datasets for Question Answering by Search and Reading
• Neural Summarization by Extracting Sentences and Words
• Multi-Perspective Context Matching for Machine Comprehension
• Improved Neural Relation Detection for Knowledge Base Question Answering
• End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
• Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning

Cited by in corpus (35)

• End-to-End Open-Domain Question Answering with BERTserini
• Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
• K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters
• Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering
• Multi-range Reasoning for Machine Comprehension
• Retrieve-and-Read: Multi-task Learning of Information Retrieval and Reading Comprehension
• Improving Question Answering with External Knowledge
• Combining Fact Extraction and Verification with Neural Semantic Matching Networks
• Efficient and Robust Question Answering from Minimal Context over Documents
• Weaver: Deep Co-Encoding of Questions and Documents for Machine Reading
• Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering
• Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering
• Multi-style Generative Reading Comprehension
• Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text
• Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification
• Joint Training of Candidate Extraction and Answer Selection for Reading Comprehension
• Controlling Risk of Web Question Answering
• Evidence Sentence Extraction for Machine Reading Comprehension
• Learning to Coordinate Multiple Reinforcement Learning Agents for Diverse Query Reformulation
• Training a Ranking Function for Open-Domain Question Answering
• NLPGym -- A toolkit for evaluating RL agents on Natural Language Processing Tasks
• Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction
• Delaying Interaction Layers in Transformer-based Encoders for Efficient Open Domain Question Answering
• EfficientQA : a RoBERTa Based Phrase-Indexed Question-Answering System
• Around the GLOBE: Numerical Aggregation Question-Answering on Heterogeneous Genealogical Knowledge Graphs with Deep Neural Networks
• JEC-QA: A Legal-Domain Question Answering Dataset
• TWEETQA: A Social Media Focused Question Answering Dataset
• Answering Open-Domain Questions of Varying Reasoning Steps from Text
• Learning Representations and Agents for Information Retrieval
• Syntax-Enhanced Pre-trained Model
• Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation
• Learning a Cost-Effective Annotation Policy for Question Answering
• Knowledge Efficient Deep Learning for Natural Language Processing
• Hierarchical Attention: What Really Counts in Various NLP Tasks
• MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering